Browser Bookmarks Cleanup

Years of "I'll come back to this" leaves most browsers with hundreds of stale or duplicated bookmarks, half labeled "Untitled" and the rest buried in folders nobody made on purpose. This demo shows what AI-driven cleanup looks like on a representative 25-bookmark messy sample — a side-by-side view of the original chaos and the AI's proposed reorganization, with explanations of why each move was made.

What this demo shows

• Reorganization — flat or randomly-foldered bookmarks regrouped under sensible category folders.
• Relabeling — "Untitled", cryptic stub titles, and outdated names rewritten to something descriptive.
• Duplicate detection — exact-URL dupes grouped so you can see what would be merged.
• Side-by-side preview — before/after view with per-folder rationale.

What the demo can't do (but the tool can)

This demo runs against a curated 25-bookmark sample. The full Browser Bookmarks Cleanup tool works with your real library and adds:

Tier overview

Basic tier — your own bookmark file (up to 2 MB, single browser), real AI categorization, HTML + JSON export back to a browser-importable format, and template saving so the tool remembers your preferred style.

Advanced / Pro tier — bulk upload across Chrome, Firefox, Safari, Edge, Opera, and Brave at the same time; smarter duplicate detection that catches near-matches (the same article saved with different wording, not just exact URL matches); broken-link checking on every URL after the AI proposes its layout; a deeper categorization model with the option to pick from several alternatives; and all five export formats: HTML, Chrome-shape JSON, CSV, Excel (one sheet per top-level folder), and a PDF audit report covering renames, duplicates, and broken links.

Smart cleanup

Categorization that respects what a URL actually is. A curated list of 230+ well-known sites (banks, email providers, cloud storage, social networks, recipe sites, news outlets) routes them directly to the right category — the AI never overrides those known signals. For the long tail, the AI prioritizes what the bookmark's title and URL clearly say over whatever messy folder it happened to be in, and flags placements with no obvious connection so you can review them.

Resolution & Clarification step. When the AI is uncertain about a bookmark, it surfaces it in a review step where you can pick the right folder, mark broken or unwanted entries for removal, or ask the AI to take another pass with the curated domain list as a strong hint. You can also run a bulk "Check links" pass that flags only verifiably-broken URLs (404 or DNS failure), or a bulk "Auto-categorize" pass that pre-fills folder choices.

Frequency-weighted ranking when you opt to upload your browsing history alongside your bookmarks. The AI sees only the top 30 domains by visit count — your full history stays server-side and is dropped after the request. Folders covering the sites you actually visit surface first.

Editing & undo

Drag-and-drop file upload for bookmarks, browsing history, passwords, and cookies. Add files one at a time, paste from clipboard, remove any with a single click.

Manual edit + drag-drop in the After view. Hover any row to reveal ✏ and 🗑 icons. Rename titles, URLs, or folder names in place; delete bookmarks or whole folders; drag any row into another folder to move it. Safety rails prevent moving a folder into itself. Everything happens instantly, no AI calls.

Search the cleaned tree by title, URL, or folder name. Matching items stay visible; non-matches hide; folders containing matches auto-expand.

One-click Undo reverts the most recent change — edit, drag, rename, delete, refine, or clarify. Click again to keep going back. A Versions dropdown also lets you jump directly to any earlier snapshot in your session.

Refine with feedback. Describe high-level changes in plain English ("consolidate my finance folders", "move all photography sites to Reference") and the AI returns just the changes; the server applies them without re-processing your whole tree.

Pro power features

Cross-device cloud sync. Save up to 20 cleaned trees under your account and re-load them from any browser or device without re-uploading the originals. Loading a saved tree skips the AI step and jumps straight to the export view.

Bulk re-evaluate on the uncertainty page. Pro 🔗 Check links checks every uncertain URL with browser-style headers; only definitively-broken links auto-flag for removal. Pro 🤖 Auto-categorize runs the curated domain list plus a focused AI pass on just those items and pre-fills each dropdown.

Per-source visibility. Upload 2+ bookmark files (say, Chrome + Firefox + Edge) and the results view opens with a Sources panel showing per-file counts, which bookmarks overlap across files, and a per-file filter tab.

Configurable folder depth. A slider in the Pro options card controls how deeply the AI nests folders (1–4 levels). Folders that would otherwise hold 9+ items automatically split into sub-folders.

Keep top-level bookmarks at the root. Opt-in toggle for users who deliberately curate their bookmark bar with quick-access shortcuts. When enabled, bookmarks already at root stay at root — the AI doesn't fold them into folders.

How we keep your data safe

Passwords and cookies (Pro) never reach the AI. A separate, audited code path handles deduplication and re-export. A build-time check blocks any change that would route credential data through an AI service. Re-downloading an encrypted credential export requires re-entering your password and accepting a short EULA, and the file works once before being deleted.

Bookmark URLs are filtered at upload and on save. URLs that could execute code in your browser (like javascript: or data: schemes) are blocked, so a malicious bookmark export can't carry hostile content back into your browser when you re-import the cleaned tree.

Per-user rate limits on every paid operation prevent a compromised session from running up unbounded AI cost.

Same engine, broader use cases

The same engine that cleans personal bookmarks generalizes to organizing unstructured data in company repositories — file shares, SharePoint, knowledge-base links — which is what makes this tool a wedge for broader content-organization use cases.

Release history

The tool has shipped 25+ versions in active development. See the live changelog on the tool page for the full release history with detail per version.

Try it

Click through the sample below, or use the "Try with your file" button to run a real AI pass against a small (≤50 bookmarks) export of your own — one free run per hour while you're trying it out.